The purpose of this paper is to research the image semantic auto-annotation method, which proposes an image semantic annotation method adopted ontology description and the image regional objects reasoning. First, the image semantic regional description model was build, and then the similar features of the region to achieve the similar semantics were annotated. Second, the algorithm focuses on the image regional object annotation description model which is related to the image semantic annotation description in the model, the spatial relation description relations between semantic objects, objects semantic relations description, abstract level structure and other key technologies, and the overall image semantic annotation would be achieved by semantic reasoning of regional objects. Finally, the search results showed that the method had better semantic retrieval performance.
[1]
SHIZhongzhi,et al.
A logical foundation for the semantic Web
,
2005
.
[2]
Yueting Zhuang,et al.
Apply semantic template to support content-based image retrieval
,
1999,
Electronic Imaging.
[3]
Maosong Sun,et al.
Automatic Image Annotation Based on WordNet and Hierarchical Ensembles
,
2006,
CICLing.
[4]
Shi Zhongzhi,et al.
A logical foundation for the semantic Web
,
2005
.
[5]
Y. Mori,et al.
Image-to-word transformation based on dividing and vector quantizing images with words
,
1999
.
[6]
Li Liu,et al.
Automatic image annotation and retrieval using subspace clustering algorithm
,
2004,
MMDB '04.